Speech Engine 3.35.4

Speech Engine 3.35.4, DB v1601, BSAPI 3.35.4 (2020-12-14)

Fixed

  • STT/KWS model AR_XL_5 has incorrect name and does not start
  • Missing KWS model AR_XL_5
  • Processing of some short recordings causes TwoGmmCalibThreshold is not finite error
  • STT preferred phrases “out of vocabulary” (OOV) warning message is now more verbose

Speech Engine 3.35.3

Speech Engine 3.35.3, DB v1601, BSAPI 3.35.3 (2020-11-24)

New

  • Internal support for SAMPA phonetic alphabet
  • Updated STT model RU_RU_A to version 4.5.0 of (updated language model)
  • Updated STT/KWS/PHNREC model AR_XL to version 5.2.0 (updated language model, changed phonemes notation to X-SAMPA)

Fixed

  • Cannot create new output stream due to hanging unfinished tasks
  • Task is not removed from pool when result is delivered via Webhook
  • Some log messages contain format placeholder instead of numbers
  • Missing <silence/> label in STT confusion network output
  • STT confusion network contains <silence/> tags with confidence greater than 1.0
  • Diarization crashes during processing
  • Diarization XL4 crashes on file with no speech
  • SID voiceprint extraction on stream is affected by previous run
  • Incorrect number of LID L4 languages in documentation

Improved

  • Database drop scripts
  • Updated document doc/Phonemes_for_STT_and_KWS.pdf

Speech Engine 3.35.0

Speech Engine 3.35.0, DB v1600, BSAPI 3.35.0 (2020-10-01)

New

  • LID model L4 was promoted to production (LID BETA_L4 renamed to LID L4)
  • Added new language tag documentation (doc/Technology_LID_L4_Language_tags.pdf)
  • Updated STT model CS_CZ_5 to version 5.2.1 (fixes faulty transcription of numbers into Roman format)
  • Added configurable STT Confusion Network threshold (in technology configuration file)

Fixed

  • STT didn’t work with 4th and older generation models after introduction of the Preferred phrases feature in SPE 3.32
  • Update from SPE 3.30 causes errors in STT result cache
  • memory leak in logging system
  • Typo in name of es-XA language in LID model L4 default language pack (es-XA7 -> es-XA)
  • Time Analysis segfaults on audio with 3+ channels
  • vpextract_s_calib.bs config file not working
  • WebSocket reply to PING control frame does not follow the protocol specification

NOTE: Due to the change in STT results content, all STT results will be removed from cache (database) during update!